{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TMCYFB65LDMSDXMYDT3SRFIIGW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0195e5fb524c961442bee02fd55d4e90e43c454eb32755b46d56bdf7a0ab0e0b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:59:02Z","title_canon_sha256":"dee9436fef3543698ae35b8fc74dc501e5da1ab3c61ae95b67a8b2e2a58814ef"},"schema_version":"1.0","source":{"id":"2402.14809","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14809","created_at":"2026-07-05T08:25:52Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14809v4","created_at":"2026-07-05T08:25:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14809","created_at":"2026-07-05T08:25:52Z"},{"alias_kind":"pith_short_12","alias_value":"TMCYFB65LDMS","created_at":"2026-07-05T08:25:52Z"},{"alias_kind":"pith_short_16","alias_value":"TMCYFB65LDMSDXMY","created_at":"2026-07-05T08:25:52Z"},{"alias_kind":"pith_short_8","alias_value":"TMCYFB65","created_at":"2026-07-05T08:25:52Z"}],"graph_snapshots":[{"event_id":"sha256:54b79a4352507f28da432651ee071cdfbba9768f28c8ac1ac0017f7ccdb72ef8","target":"graph","created_at":"2026-07-05T08:25:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.14809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ability of Large Language Models (LLMs) to critique and refine their reasoning is crucial for their application in evaluation, feedback provision, and self-improvement. This paper introduces CriticBench, a comprehensive benchmark designed to assess LLMs' abilities to critique and rectify their reasoning across a variety of tasks. CriticBench encompasses five reasoning domains: mathematical, commonsense, symbolic, coding, and algorithmic. It compiles 15 datasets and incorporates responses from three LLM families. Utilizing CriticBench, we evaluate and dissect the performance of 17 LLMs in g","authors_text":"Haowei Liu, Ruilin Luo, Tian Liang, Yujiu Yang, Zhibin Gou, Zicheng Lin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:59:02Z","title":"CriticBench: Benchmarking LLMs for Critique-Correct Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14809","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:57bd1304527fc8c067685b479b7ced0677edd0f85b308be8a0a4f92723bd06c5","target":"record","created_at":"2026-07-05T08:25:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0195e5fb524c961442bee02fd55d4e90e43c454eb32755b46d56bdf7a0ab0e0b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:59:02Z","title_canon_sha256":"dee9436fef3543698ae35b8fc74dc501e5da1ab3c61ae95b67a8b2e2a58814ef"},"schema_version":"1.0","source":{"id":"2402.14809","kind":"arxiv","version":4}},"canonical_sha256":"9b058287dd58d921dd981cf7289508359bce355c722c3d0480efdd74eb97917e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b058287dd58d921dd981cf7289508359bce355c722c3d0480efdd74eb97917e","first_computed_at":"2026-07-05T08:25:52.733767Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:52.733767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DbjCagQynEC3YZHMbP+FtNhiOPWK6PZiuY7vmdt4K0T+0inY2BnKBl4qyfSAOAfbgAZVlJu1lSJuCEONSiSgCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:52.734223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14809","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57bd1304527fc8c067685b479b7ced0677edd0f85b308be8a0a4f92723bd06c5","sha256:54b79a4352507f28da432651ee071cdfbba9768f28c8ac1ac0017f7ccdb72ef8"],"state_sha256":"005af9f155473795fedfd6460df076feb98867f27008bc9af8f6c7130793a296"}